© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74565
    Prev
    Next
    INDEX
    Explanations

    is located

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mangá
    -1.71
     cũng
    -1.63
    さてさて
    -1.61
    ]-->
    -1.51
     ++)
    -1.50
     austral
    -1.49
     Repubblica
    -1.49
    スポンサーリンク
    -1.46
     garçon
    -1.45
    داً
    -1.45
    POSITIVE LOGITS
     ormai
    1.76
     is
    1.74
     seguras
    1.65
     erstes
    1.60
     diğer
    1.59
    其他
    1.59
     다른
    1.49
     zweiten
    1.45
     bestimmten
    1.44
     rápidas
    1.41
    Activations Density 0.060%

    No Known Activations